@inproceedings{si-kong-2020-rong,
title = "融入对话上文整体信息的层次匹配回应选择(Learning Overall Dialogue Information for Dialogue Response Selection)",
author = "Si, Bowen and
Kong, Fang",
editor = "Sun, Maosong and
Li, Sujian and
Zhang, Yue and
Liu, Yang",
booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
month = oct,
year = "2020",
address = "Haikou, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2020.ccl-1.26",
pages = "266--276",
abstract = "对话是一个顺序交互的过程,回应选择旨在根据已有对话上文选择合适的回应,是自然语言处理领域的研究热点。已有研究取得了一定的成功,但仍然存在两个突出的问题。一是现有的编码器在挖掘对话文本语义信息上尚存在不足;二是只考虑每一回合对话与备选回应之间的关系,忽视了对话上文的整体语义信息。针对问题一,本文借助多头自注意力机制有效捕捉对话文本的语义信息;针对问题二,整合对话上文的整体语义信息,分别从单词、句子以及整体对话上文三个层次与备选回应进行匹配,充分保证匹配信息的完整。在Ubuntu Corpus V1和Douban Conversation Corpus数据集上的对比实验表明了本文给出方法的有效性。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="si-kong-2020-rong">
<titleInfo>
<title>融入对话上文整体信息的层次匹配回应选择(Learning Overall Dialogue Information for Dialogue Response Selection)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Haikou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>对话是一个顺序交互的过程,回应选择旨在根据已有对话上文选择合适的回应,是自然语言处理领域的研究热点。已有研究取得了一定的成功,但仍然存在两个突出的问题。一是现有的编码器在挖掘对话文本语义信息上尚存在不足;二是只考虑每一回合对话与备选回应之间的关系,忽视了对话上文的整体语义信息。针对问题一,本文借助多头自注意力机制有效捕捉对话文本的语义信息;针对问题二,整合对话上文的整体语义信息,分别从单词、句子以及整体对话上文三个层次与备选回应进行匹配,充分保证匹配信息的完整。在Ubuntu Corpus V1和Douban Conversation Corpus数据集上的对比实验表明了本文给出方法的有效性。</abstract>
<identifier type="citekey">si-kong-2020-rong</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.26</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>266</start>
<end>276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 融入对话上文整体信息的层次匹配回应选择(Learning Overall Dialogue Information for Dialogue Response Selection)
%A Si, Bowen
%A Kong, Fang
%Y Sun, Maosong
%Y Li, Sujian
%Y Zhang, Yue
%Y Liu, Yang
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 October
%I Chinese Information Processing Society of China
%C Haikou, China
%G Chinese
%F si-kong-2020-rong
%X 对话是一个顺序交互的过程,回应选择旨在根据已有对话上文选择合适的回应,是自然语言处理领域的研究热点。已有研究取得了一定的成功,但仍然存在两个突出的问题。一是现有的编码器在挖掘对话文本语义信息上尚存在不足;二是只考虑每一回合对话与备选回应之间的关系,忽视了对话上文的整体语义信息。针对问题一,本文借助多头自注意力机制有效捕捉对话文本的语义信息;针对问题二,整合对话上文的整体语义信息,分别从单词、句子以及整体对话上文三个层次与备选回应进行匹配,充分保证匹配信息的完整。在Ubuntu Corpus V1和Douban Conversation Corpus数据集上的对比实验表明了本文给出方法的有效性。
%U https://aclanthology.org/2020.ccl-1.26
%P 266-276
Markdown (Informal)
[融入对话上文整体信息的层次匹配回应选择(Learning Overall Dialogue Information for Dialogue Response Selection)](https://aclanthology.org/2020.ccl-1.26) (Si & Kong, CCL 2020)
ACL